https://github.com/samuelsoaress/deploy-model-web

Web application with the Tensorflow model for recognizing manuscrits numbers
https://github.com/samuelsoaress/deploy-model-web

cnn-for-visual-recognition data-augmentation deploy-machine-learning recognizing-numbers tensorflow-model web-application

Last synced: 8 months ago
JSON representation

Web application with the Tensorflow model for recognizing manuscrits numbers

• Host: GitHub
• URL: https://github.com/samuelsoaress/deploy-model-web
• Owner: samuelsoaress
• Created: 2020-05-10T16:55:23.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2021-02-17T20:20:19.000Z (over 4 years ago)
• Last Synced: 2025-01-08T06:32:08.012Z (10 months ago)
• Topics: cnn-for-visual-recognition, data-augmentation, deploy-machine-learning, recognizing-numbers, tensorflow-model, web-application
• Language: Jupyter Notebook
• Homepage: https://samuelsoaress.github.io/deploy-model-web/
• Size: 35.2 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# deploy-model-web

 

This repository contains a simple case of a Tensorflow neural network model implemented in the web application for the recognition of numbers using TensorflowJS

## about the base

The MNIST database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems. The database is also widely used for training and testing in the field of machine learning. More about [MNIST](https://en.wikipedia.org/wiki/MNIST_database)

### imgs

![](img/numbers.png)

## about model

To train this model, convolutional neural networks were used together with data augmentation techniques. training 60,000 images and testing with 10,000. right after training with the test base.